Pith Number

pith:KN4XLYFF

pith:2024:KN4XLYFFHF2Q5R3ERYDWPLIKGT

not attested not anchored not stored refs pending

Reward-Robust RLHF in LLMs

Chao Yu, Dong Yan, Jialian Li, Jian Xie, Xingzhou Lou, Yiping Zhang, Yuan Shen, Yu Wang, Yuzi Yan

arxiv:2409.15360 v3 · 2024-09-18 · cs.LG · cs.AI · cs.CL

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{KN4XLYFFHF2Q5R3ERYDWPLIKGT}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Cited by

9 papers in Pith

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization

The Hidden Bias of Process Reward Models:PRISM for Rewarding the Right Reasoning

A Unifying Lens on Reward Uncertainty in RLHF

Efficient Preference Poisoning Attack on Offline RLHF

Quantifying Empirical Compute-Supervision Tradeoffs in RLVR

Receipt and verification

First computed	2026-07-05T09:21:28.367341Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

537975e0a539750ec7648e0767ad0a34d0c3f69bfd438ddca04d97e2f14d7b2c

Aliases

arxiv: 2409.15360 · arxiv_version: 2409.15360v3 · doi: 10.48550/arxiv.2409.15360 · pith_short_12: KN4XLYFFHF2Q · pith_short_16: KN4XLYFFHF2Q5R3E · pith_short_8: KN4XLYFF

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/KN4XLYFFHF2Q5R3ERYDWPLIKGT \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 537975e0a539750ec7648e0767ad0a34d0c3f69bfd438ddca04d97e2f14d7b2c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9308465f6c3f21be2d81cbd5bac84d94569a3ff21979e7a3c9b8d1d688fd4d79",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-09-18T02:35:41Z",
    "title_canon_sha256": "1080627b3081518dbe421875b24ddb43f46812acdf80da61149b8039a786ad59"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2409.15360",
    "kind": "arxiv",
    "version": 3
  }
}